ultralytics/cfg/datasets/VOC.yaml

# Ultralytics YOLO 🚀, AGPL-3.0 license
# PASCAL VOC dataset http://host.robots.ox.ac.uk/pascal/VOC by University of Oxford
# Documentation: # Documentation: https://docs.ultralytics.com/datasets/detect/voc/
# Example usage: yolo train data=VOC.yaml
# parent
# ├── ultralytics
# └── datasets
#     └── VOC  ← downloads here (2.8 GB)

# Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..]
path: ../datasets/VOC
train: # train images (relative to 'path')  16551 images
  - images/train2012
  - images/train2007
  - images/val2012
  - images/val2007
val: # val images (relative to 'path')  4952 images
  - images/test2007
test: # test images (optional)
  - images/test2007

# Classes
names:
  0: aeroplane
  1: bicycle
  2: bird
  3: boat
  4: bottle
  5: bus
  6: car
  7: cat
  8: chair
  9: cow
  10: diningtable
  11: dog
  12: horse
  13: motorbike
  14: person
  15: pottedplant
  16: sheep
  17: sofa
  18: train
  19: tvmonitor

# Download script/URL (optional) ---------------------------------------------------------------------------------------
download: |
  import xml.etree.ElementTree as ET

  from tqdm import tqdm
  from ultralytics.utils.downloads import download
  from pathlib import Path

  def convert_label(path, lb_path, year, image_id):
      def convert_box(size, box):
          dw, dh = 1. / size[0], 1. / size[1]
          x, y, w, h = (box[0] + box[1]) / 2.0 - 1, (box[2] + box[3]) / 2.0 - 1, box[1] - box[0], box[3] - box[2]
          return x * dw, y * dh, w * dw, h * dh

      in_file = open(path / f'VOC{year}/Annotations/{image_id}.xml')
      out_file = open(lb_path, 'w')
      tree = ET.parse(in_file)
      root = tree.getroot()
      size = root.find('size')
      w = int(size.find('width').text)
      h = int(size.find('height').text)

      names = list(yaml['names'].values())  # names list
      for obj in root.iter('object'):
          cls = obj.find('name').text
          if cls in names and int(obj.find('difficult').text) != 1:
              xmlbox = obj.find('bndbox')
              bb = convert_box((w, h), [float(xmlbox.find(x).text) for x in ('xmin', 'xmax', 'ymin', 'ymax')])
              cls_id = names.index(cls)  # class id
              out_file.write(" ".join(str(a) for a in (cls_id, *bb)) + '\n')


  # Download
  dir = Path(yaml['path'])  # dataset root dir
  url = 'https://github.com/ultralytics/assets/releases/download/v0.0.0/'
  urls = [f'{url}VOCtrainval_06-Nov-2007.zip',  # 446MB, 5012 images
          f'{url}VOCtest_06-Nov-2007.zip',  # 438MB, 4953 images
          f'{url}VOCtrainval_11-May-2012.zip']  # 1.95GB, 17126 images
  download(urls, dir=dir / 'images', curl=True, threads=3, exist_ok=True)  # download and unzip over existing paths (required)

  # Convert
  path = dir / 'images/VOCdevkit'
  for year, image_set in ('2012', 'train'), ('2012', 'val'), ('2007', 'train'), ('2007', 'val'), ('2007', 'test'):
      imgs_path = dir / 'images' / f'{image_set}{year}'
      lbs_path = dir / 'labels' / f'{image_set}{year}'
      imgs_path.mkdir(exist_ok=True, parents=True)
      lbs_path.mkdir(exist_ok=True, parents=True)

      with open(path / f'VOC{year}/ImageSets/Main/{image_set}.txt') as f:
          image_ids = f.read().strip().split()
      for id in tqdm(image_ids, desc=f'{image_set}{year}'):
          f = path / f'VOC{year}/JPEGImages/{id}.jpg'  # old img path
          lb_path = (lbs_path / f.name).with_suffix('.txt')  # new label path
          f.rename(imgs_path / f.name)  # move image
          convert_label(path, lb_path, year, id)  # convert labels to YOLO format